Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.

# st: RE: graphic observed means and confidence intervals over time

 From Nick Cox To "'statalist@hsphsun2.harvard.edu'" Subject st: RE: graphic observed means and confidence intervals over time Date Fri, 18 Nov 2011 17:09:19 +0000

```See -xtgraph- (SSC). Recent postings have suggested that there are bugs in this, but I can't comment.

SJ-10-1 gr0045  . . . . . . . . . . . . . Speaking Stata: The statsby strategy
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  N. J. Cox
Q1/10   SJ 10(1):143--151                                (no commands)
demonstrates the use of statsby to prepare a reduced
dataset for subsequent graphing

Nick
n.j.cox@durham.ac.uk

Lloyd Dumont

I
have a large dataset of survey responses from individuals over time.  Each observation comes from one of 5 years,
though the individual respondents cannot be linked between rounds, so this is
not panel data.

A
reviewer has suggested that I plot the means of a few variables over time.  That is easy.  But, he has said he would like to see the standard errors on this graph
as well.  If I am correctly understanding
him, he wants to see a simple line plot with a solid line representing the
mean, and then dotted lines representing a confidence interval around that
mean, over time.
If
I were just plotting the mean, I would use -collapse-, create means by year,
and call it a day.  But, if I want
confidence intervals around these means, what is the best way to do that?  Should I still do it using -collapse-, or is
there a shortcut for plotting observed (as opposed to predicted or fitted)
means and their confidence intervals?

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/
```